diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 21:14:25 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 21:14:25 -0700 |
| commit | fe29f997b43d502fda3353b6c59894e962de48f9 (patch) | |
| tree | 8f069d5ac8da00a2e2a8426f28dc6fcc528650d7 | |
| parent | b8db6fb555b8d29900015d9829bce1c372b8b1b9 (diff) | |
| download | sandcrawler-fe29f997b43d502fda3353b6c59894e962de48f9.tar.gz sandcrawler-fe29f997b43d502fda3353b6c59894e962de48f9.zip | |
pdfextract: catch poppler.LockedDocumentError
| -rw-r--r-- | python/sandcrawler/pdfextract.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py index 97c2f3b..e7bfa43 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -167,7 +167,7 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr ) # this call sometimes fails an returns an AttributeError page0rect = page0.page_rect() - except AttributeError as e: + except (AttributeError, poppler.LockedDocumentError) as e: # may need to expand the set of exceptions caught here over time, but # starting with a narrow set return PdfExtractResult( |